paper-with-me

홈 › Papers

CASTER: Breaking the Cost-Performance Barrier in Multi-Agent Orchestration via Context-Aware Strategy for Task Efficient Routing

2026-01-27 · Shanyv Liu, Xuyang Yuan, Tao Chen, Zijun Zhan, Zhu Han, Danyang Zheng, Weishan Zhang, Shaohua Cao arxiv

Graph-based Multi-Agent Systems (MAS) enable complex cyclic workflows but suffer from inefficient static model allocation, where deploying strong models uniformly wastes computation on trivial sub-tasks. We propose CASTER (Context-Aware Strategy for Task Efficient Routing), a lightweight router for dynamic model selection in graph-based MAS. CASTER employs a Dual-Signal Router that combines semantic embeddings with structural meta-features to estimate task difficulty. During training, the router self-optimizes through a Cold Start to Iterative Evolution paradigm, learning from its own routing failures via on-policy negative feedback. Experiments using LLM-as-a-Judge evaluation across Software Engineering, Data Analysis, Scientific Discovery, and Cybersecurity demonstrate that CASTER reduces inference cost by up to 72.4% compared to strong-model baselines while matching their success rates, and consistently outperforms both heuristic routing and FrugalGPT across all domains.

📄 PDF Abstract BibTeX arXiv:2601.19793

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Breaking the Tuning Barrier: Zero-Hyperparameters Yield Multi-Corner Analysis Via Learned Priors

2026-03-13 · Wei W. Xing, Kaiqi Huang, Jiazhan Liu, Hong Qiu 외 arxiv

Yield Multi-Corner Analysis validates circuits across 25+ Process-Voltage-Temperature corners, resulting in a combinatorial simulation cost of $O(K \times N)$ where $K$ denotes corners and $N$ exceeds $10^4$ samples per …

S$^2$-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency

2025-02-07 · Yuting Zeng, Weizhe Huang, Lei Jiang, Tongxuan Liu 외

Large language models (LLMs) have demonstrated remarkable capabilities across various natural language processing (NLP) scenarios, but they still face challenges when handling complex arithmetic and logical reasoning tas…

Logical Reasoning

U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster

2026-04-10 · Salva Rühling Cachay, Duncan Watson-Parris, Rose Yu arxiv

AI-based weather forecasting now rivals traditional physics-based ensembles, but state-of-the-art (SOTA) models rely on specialized architectures and massive computational budgets, creating a high barrier to entry. We de…

Weather Forecasting

WaveForward: An Omnidirectional Passive Wheeled Quadruped Robot with Casters

2026-06-24 · Chuanlin Zhao, Qifeng Zheng, Shuhan Wang, Tiancheng Ma 외 arxiv

Wheeled-legged robots possess both agile mobility for traversing complex terrains and high efficiency, making them suitable for long-distance transportation applications. Conventional actuated wheeled robots require spec…

Breaking the Reclustering Barrier in Centroid-based Deep Clustering

2024-11-04 · Lukas Miklautz, Timo Klein, Kevin Sidak, Collin Leiber 외

This work investigates an important phenomenon in centroid-based deep clustering (DC) algorithms: Performance quickly saturates after a period of rapid early gains. Practitioners commonly address early saturation with pe…

ClusteringDeep ClusteringImage ClusteringUnsupervised Image Classification